GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification

TL;DR

GENIE-ASI introduces a training-free LLM-based method for analog subcircuit identification, reducing reliance on expert knowledge and large datasets, and demonstrates promising results across various circuit complexities.

Contribution

It is the first to utilize a training-free LLM approach for analog subcircuit identification, combining in-context learning with executable code generation.

Findings

Achieves perfect performance on simple structures (F1-score=1.0)

Remains competitive on moderate abstractions (F1-score=0.81)

Shows potential on complex subcircuits (F1-score=0.31)

Abstract

Analog subcircuit identification is a core task in analog design, essential for simulation, sizing, and layout. Traditional methods often require extensive human expertise, rule-based encoding, or large labeled datasets. To address these challenges, we propose GENIE-ASI, the first training-free, large language model (LLM)-based methodology for analog subcircuit identification. GENIE-ASI operates in two phases: it first uses in-context learning to derive natural language instructions from a few demonstration examples, then translates these into executable Python code to identify subcircuits in unseen SPICE netlists. In addition, to evaluate LLM-based approaches systematically, we introduce a new benchmark composed of operational amplifier netlists (op-amps) that cover a wide range of subcircuit variants. Experimental results on the proposed benchmark show that GENIE-ASI matches rule-based performance on simple structures (F1-score = 1.0), remains competitive on moderate abstractions (F1-score = 0.81), and shows potential even on complex subcircuits (F1-score = 0.31). These findings demonstrate that LLMs can serve as adaptable, general-purpose tools in analog design automation, opening new research directions for foundation model applications in analog design automation.